We proposed a blind dereverberation method based on spectral subtraction by Multi-Channel Least Mean Square (MCLMS) algorithm for distant-talking speech recognition in our previous study . In this paper, we discuss the problems of the proposed method and present some solutions. In a distant-talking environment, the length of channel impulse response is longer than the short-term spectral analysis window. By treating the late reverberation as additive noise, a noise reduction technique based on spectral subtraction was proposed to estimate power spectrum of the clean speech using power spectra of the distorted speech and the unknown impulse responses. To estimate the power spectra of the impulse responses, a Variable Step-Size Unconstrained MCLMS (VSS-UMCLMS) algorithm for identifying the impulse responses in a time domain was extended to a frequency domain. To reduce the effect of the estimation error of channel impulse response, we normalize the early reverberation by CMN instead of the spectral subtraction used by the estimated impulse response in this paper. Furthermore, our proposed method is combined with a conventional delay-and-sum beamforming. We conducted the experiments on distorted speech signal simulated by convolving multi-channel impulse responses with clean speech. The modified proposed method achieved a relative error reduction rate of 22.7% from conventional CMN and 12.0% from the original proposed method, respectively. By combining the modified proposed method with the beamforming, a furthermore improvement (relative error reduction rate of 23.3%) was achieved.
Bibliographic reference. Wang, L. / Nakagawa, Seiichi / Kitaoka, Norihide (2008): "Blind dereverberation based on CMN and spectral subtraction by multi-channel LMS algorithm", In INTERSPEECH-2008, 1032-1035.